Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Code/script snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     certif
    -0.07
     decline
    -0.06
     waterfront
    -0.06
    alsy
    -0.06
    tot
    -0.06
     Butt
    -0.06
    -corner
    -0.06
    Hall
    -0.06
     interess
    -0.06
    ypy
    -0.06
    POSITIVE LOGITS
     двух
    0.09
     WOM
    0.08
    }),
    0.07
    _removed
    0.07
    ий
    0.07
     무슨
    0.07
    になり
    0.06
     تخ
    0.06
     níž
    0.06
     其他
    0.06
    Act Density 0.000%

    No Known Activations